Sebastian Foersch
@twittlabs.bsky.social
Board-certified Pathologist, Former Member of the Board of Directors of the German Society of Pathology (no medical advice-opinions are my own) https://www.unimedizin-mainz.de/pathologie/das-institut/mitarbeiter/aerzte/foersch.html
KI in der Medizin: 🏥 Forscher:innen des @ekfzdigital.bsky.social haben Chancen & Risiken systematisch analysiert. Sie warnen vor Gefahren für Patientensicherheit, Datenschutz & klinische Entscheidungsprozesse. Sie zeigen aber auch Wege für einen verantwortungsvollen Einsatz auf. ℹ️ tud.link/9p14qb
Calling all researchers using Anthropic's AI model Claude: how are you using the new Claude Fable 5 model in your research? We want to hear about the most impressive things it's built for your research projects or left you asking what the fuss is all about. Let us know.
After years of work, our paper is now out in npj Digital Medicine: we developed an AI for polyp detection and tested it in a randomized clinical study in GI practices. www.nature.com/articles/s41... The software is freely available via our lab website. #AI #Gastroenterology #DigitalHealth
🙌 Welcome to the ESMO Sarcoma and Rare Cancers Congress 2026! 12–14 March, Lugano. Hope, care and action drive breakthroughs. Thank you for being part of this progress. #ESMORareCancers26 #esmomeetings 🔗 https://ow.ly/B9qr50YsINg
Launching The Lancet Pulse 🚀 From xenotransplantation to psychedelic drug research, The Lancet Pulse translates science into practical insights about new clinical research—and why it matters. Listen today: spkl.io/63327AvjMX
Fantastic work by @thelancet.com team. It was wonderful chatting with you. Check out our episode about #AI in #Pathology 🔬🤖🧬 and the other cool topics as well 🚀 #Podcast #Clinical #Research #TheLancet #Pulse #MedSky
The Lancet@thelancet.com · 6mo agoLaunching The Lancet Pulse 🚀 From xenotransplantation to psychedelic drug research, The Lancet Pulse translates science into practical insights about new clinical research—and why it matters. Listen today: spkl.io/63327AvjMX
🎇 Die Allianz der Rhein-Main-Universitäten (RMU) @goetheuni.bsky.social, @unimainz.bsky.social und @tuda.bsky.social wünscht einen guten Start in ein gesundes und glückliches neues Jahr - cheers to a healthy, happy and successful 2026 🎇 #RMU #RheinMainUniversitäten #Verbund #FrohesNeues
In the latest episode of the AI Grand Rounds podcast, Dr. Zak Kohane, editor-in-chief of NEJM AI, explains why this year’s advances in #AI were personal, why it’s spreading fast, and why its most profound theme is values. Full episode: nejm.ai/ep37 #MedSky #MLSky
Humans and machines make the same mistakes — just for different reasons. On NEJM AI Grand Rounds, Dr. Laura Zwaan discusses bias, cognition, and #AI. Full episode: nejm.ai/ep36 #MedSky #MLSky
Now out in @natcomputsci.nature.com: "Adaptive validation strategies for real-world clinical artificial intelligence" It was a pleasure working on this piece with @jnkt.bsky.social, excited to finally see it published! #medicalAI #clinicalAI #digitalhealth #translationalresearch
Nature Computational Science@natcomputsci.nature.com · 9mo ago📢 @fionakolbinger.bsky.social and @jnkt.bsky.social characterize the discordance between metrics used to evaluate AI tools and their clinical impact, proposing a framework to reduce this disconnect. www.nature.com/articles/s43... @tudresden.bsky.social @ekfzdigital.bsky.social 🔓 rdcu.be/eQmQp
#DFG verlängert Förderung für exzellente Forschung an der Universitätsmedizin Mainz: 3. Förderperiode für #Sonderforschungsbereich zur Entwicklung neuer Immuntherapien gegen #Krebs unter Federführung der #UnimedizinMainz 👉 https://sohub.io/qdbx
📢 @fionakolbinger.bsky.social and @jnkt.bsky.social characterize the discordance between metrics used to evaluate AI tools and their clinical impact, proposing a framework to reduce this disconnect. www.nature.com/articles/s43... @tudresden.bsky.social @ekfzdigital.bsky.social 🔓 rdcu.be/eQmQp
Adaptive validation strategies for real-world clinical artificial intelligence - Nature Computational Science
Technical metrics used to evaluate medical artificial intelligence tools often fail to predict their clinical impact. We characterize this discordance and propose a framework of study designs to guide...
nature.com
AI models are 50% more sycophantic than humans go.nature.com/4nr2HIL
AI chatbots are sycophants — researchers say it's harming science
Nature asked researchers who use artificial intelligence how its propensity for people-pleasing affects their work — and what they are doing to mitigate it.
go.nature.com
A new study introduces a publicly available script concordance test benchmark that reveals important limitations in the clinical reasoning capabilities of leading LLMs, particularly in processing new information under uncertainty. nejm.ai/3KlD5yX @liamgmccoy.bsky.social #AI #MedSky #MLSky
Der #Hochschulwettbewerb 2026 startet! Wir suchen Ideen zur Medizin der Zukunft: von KI und Telemedizin bis hin zu gesellschaftlichen und künstlerischen Perspektiven. Die besten 10 Projekte erhalten je 10.000 €! Ihr könnt euch bis zum 30.11.2025 bewerben. Alle Infos: www.hochschulwettbewerb.net/2026
Die Uniklinik RWTH Aachen sucht dringend Blutspender*innen, um dem Engpass in der Versorgung zu begegnen. Ihr könnt innenstadtnah spenden in der Großkölnstraße 32 in Aachen. 👍Achtung: Eine Spende in der Uniklinik selbst ist nicht möglich. ➡️ www.ukaachen.de/kliniken-ins...
MedAgentBench, a comprehensive benchmark designed to evaluate the agentic capabilities of large language models in realistic EHR environments, provides a critical foundation for advancing and integrating LLM agents into clinical workflows. Learn more: nejm.ai/45AUXwS #AI #MedSky #MLSky
Bluesky CEO Jay Graber emphasized the importance of critical thinking and developing a generalist skillset for the AI era.
Bluesky's CEO warns you shouldn't 'fully outsource your thinking' to AI
Bluesky CEO Jay Graber emphasized the importance of critical thinking and developing a generalist skillset for the AI era.
businessinsider.com
📣 ERC Synergy Grant 2026 call for proposals is now open! Application deadline 5 November 2025. 📝 Groups of 2-4 researchers 📝 Jointly addressing ambitious problems & with different skills Application portal 👉 europa.eu/!XpwptY General info 👉 europa.eu/!PR6gt8 #ERCSyG #FrontierResearch
Thank you for sharing! It was a pleasure working on this, together with @twittlabs.bsky.social , @jnkt.bsky.social and many others...
NEJM AI@ai.nejm.org · last yr.Case Study by J. Clusmann et al.: Incidental Prompt Injections on Vision–Language Models in Real-Life Histopathology nejm.ai/4mrSoEW @janclusmann.bsky.social #AI #MedSky #DigitalHealth
Case Study by J. Clusmann et al.: Incidental Prompt Injections on Vision–Language Models in Real-Life Histopathology nejm.ai/4mrSoEW @janclusmann.bsky.social #AI #MedSky #DigitalHealth
Handwritten labels and watermarks on histopathological images can unintentionally act as prompt injections, misleading vision–language models and resulting in inaccurate outputs that highlight a critical vulnerability in medical #AI systems. Learn more: nejm.ai/4mrSoEW #MedSky #DigitalHealth
A big day for medical A.I. publications! —Oncology agent for decision making nature.com/articles/s43... —Forecasting infectious diseases nature.com/articles/s43... —Dermatology nature.com/articles/s41... —Predicting stroke www.nature.com/articles/s41...
Development and validation of an autonomous artificial intelligence agent for clinical decision-making in oncology - Nature Cancer
Ferber et al. present an autonomous artificial intelligence agent system for deployment of specialized medical oncology computational tools, validating their system across various clinical scenarios r...
nature.com
very happy to share our new paper on LLM-based tumor board agents. Submitted August 2024, published in @natcancer.nature.com today ☺️ Led by Dyke Ferber www.nature.com/articles/s43...
Development and validation of an autonomous artificial intelligence agent for clinical decision-making in oncology - Nature Cancer
Ferber et al. present an autonomous artificial intelligence agent system for deployment of specialized medical oncology computational tools, validating their system across various clinical scenarios r...
nature.com
Dream Police alert: InterpolAI for enhanced 3D imaging (CODA, MRI, EM, confocal). Read about and InterpolAI here: www.nature.com/articles/s41...
InterpolAI: deep learning-based optical flow interpolation and restoration of biomedical images for improved 3D tissue mapping
Nature Methods - InterpolAI leverages optimal flow-based artificial intelligence to produce synthetic images between pairs of images for diverse three-dimensional image types. InterpolAI is more...
nature.com
Finally out, in NEJM AI! Everyday labels and watermarks can override medical knowledge of vision language models, just by their presence. Was a lot of fun to work on this with @twittlabs.bsky.social , @jnkt.bsky.social and many others
Sebastian Foersch@twittlabs.bsky.social · last yr.Excited to share our new publication in @ai.nejm.org „Incidental Prompt Injections on Vision-Language Models in Real-Life Histopathology“. Important work together with our amazing colleagues @janclusmann.bsky.social @jnkt.bsky.social @markuseckstein3.bsky.social et al. ai.nejm.org/stoken/defau...
Excited to share our new publication in @ai.nejm.org „Incidental Prompt Injections on Vision-Language Models in Real-Life Histopathology“. Important work together with our amazing colleagues @janclusmann.bsky.social @jnkt.bsky.social @markuseckstein3.bsky.social et al. ai.nejm.org/stoken/defau...
Incidental Prompt Injections on Vision–Language Models in Real-Life Histopathology
Vision–language models (VLMs) can analyze multimodal medical data. However, a significant weakness of VLMs is their susceptibility to prompt injection attacks. Here, the model receives conflicting ...
ai.nejm.org
A pie graph worth keeping in mind as the NIH budget plummets jamanetwork.com/journals/jam... for 356 new FDA drugs approved
We are pushing for an acceleration… and it might end up coming. It has been way too long until Europe started to slowly get moving. Still need to do a lot
Jakob Nikolas Kather@jnkt.bsky.social · 2y agoReally disappointed how slowly Europe (especially Germany) is moving these days Obviously, to compete with US/China on any relevant topic (AI / economy / defense), we need more European integration, joing funding, joint efforts - and much much faster more resources: eu-acc.com @euacc.bsky.social
